Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 12813
    Prev
    Next
    INDEX
    Explanations

    words related to lifestyle choices

    oai_token-act-pair · gpt-3.5-turbo

    references to lifestyle choices and factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rations
    -0.84
    umbn
    -0.76
    essee
    -0.76
    zynski
    -0.74
    enary
    -0.72
    enic
    -0.72
    ioxide
    -0.69
    Ni
    -0.68
    dll
    -0.68
     Cosponsors
    -0.67
    POSITIVE LOGITS
     lifestyle
    1.05
     habits
    1.01
     choices
    0.98
     lifestyles
    0.92
     allowance
    0.77
     regimen
    0.76
     modification
    0.76
     necessities
    0.75
    ifestyle
    0.75
     preferences
    0.73
    Activations Density 0.023%

    No Known Activations